© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1136
    Prev
    Next
    INDEX
    Explanations

    mentions of large quantities or sums of money

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating large quantities of something, particularly in numerical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    netflix
    -0.74
    gow
    -0.72
    dict
    -0.68
    chart
    -0.67
    pret
    -0.67
    terms
    -0.67
    icism
    -0.67
    vale
    -0.66
    chat
    -0.66
    hess
    -0.65
    POSITIVE LOGITS
     thousands
    2.08
     millions
    1.75
     thous
    1.53
     billions
    1.53
     Thousands
    1.41
     thousand
    1.41
     trillions
    1.32
     hundreds
    1.26
     tens
    1.09
     kilometres
    1.09
    Activations Density 0.040%

    No Known Activations